INDEX

Explanations

references to the northern geographical locations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

loquent

-0.16

ocha

-0.15

aren

-0.15

onis

-0.15

eon

-0.15

Riy

-0.14

ignite

-0.14

omp

-0.14

aign

-0.14

 bottoms

-0.14

POSITIVE LOGITS

most

0.19

fol

0.16

appings

0.15

folk

0.15

western

0.15

ollo

0.15

fol

0.15

 gere

0.15

ëĳĲ

0.14

/front

0.14

Activations Density 0.048%

references to the northern geographical locations

No Comments

No Known Activations